Rail
NPM · RAIL-MCP
Budgets, propose-then-approve, and receipts for agents that buy for a human. Dry-run by default.
Available components
Last scanned (8 minutes ago)
Scores higher than 83% of npm servers
Category Finance and Payments
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 0 of 4 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 25 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability82
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 607 tokens (~86/item across 7 items; 7 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management87
- Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 25 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 22 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.
- 20 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.
- 14 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Oct 26 +1
- Security disclosure: unverified → fail ▼ functional
- 11 Oct 26 +5
- Security disclosure: fail → unverified ▼ functional
- Stability: unverified → 0.40 ▲ functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 25 Oct 2026 · Analysed npm/rail-mcp@0.1.1
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 4 packages
| Packages resolved | 4 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
decide_proposal Decide proposal ~148
Approve or reject one pending proposal. This is the step a human should confirm. decision=approve settles the purchase: in the default dry-run mode it writes a settled_dry_run receipt, stamps a fake settlement ref (lsrq_dry_…), and decrements the remaining budget, without calling the network. decision=reject spends nothing and writes no receipt. The proposal can be decided only once; repeating the call does not settle again. Live charging stays off unless separate live gates are set on purpose.
| Name | Type | Req | Description |
|---|---|---|---|
| decision | string | yes | approve settles; reject spends nothing |
| note | string | – | Optional decision note |
| proposal_id | string | yes | Proposal id (prop_…) |
No output schema declared.
No examples provided.
get_budget Get budget ~41
Read the active budget, amount spent, amount remaining, and the count of pending proposals. Does not change the ledger, spend money, or contact Stripe or Link.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_receipts Get receipts ~46
Read receipts, newest first, including dry-run settlements and refunds. Does not refund, spend money, or contact Stripe or Link.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Max receipts to return |
No output schema declared.
No examples provided.
list_proposals List proposals ~61
Read purchase proposals filtered by status: pending (default), approved, rejected, or all. Does not approve, reject, spend money, or contact Stripe or Link.
| Name | Type | Req | Description |
|---|---|---|---|
| status | string | – | Filter: pending (default), approved, rejected, or all |
No output schema declared.
No examples provided.
propose_purchase Propose purchase ~131
Record a pending purchase intent only. Moves no money, creates no receipt, approves no card, and does not contact Stripe or Link. Needs a later human approval via decide_proposal before anything settles. When a budget exists and the amount is above what remains, the proposal is stored with over_budget set and still spends nothing.
| Name | Type | Req | Description |
|---|---|---|---|
| amount_usd | number | yes | Purchase amount in USD |
| merchant | string | yes | Merchant or seller name |
| rationale | string | – | Why the agent wants this |
| sku | string | – | SKU or product identifier |
| url | string | – | Product or checkout URL |
No output schema declared.
No examples provided.
refund_receipt Refund receipt ~91
Reverse a settled dry-run receipt and restore that amount to the remaining budget. This is the step a human should confirm. Does not contact Stripe or Link. A receipt can be refunded only once; repeating the call does not refund again. Refuses receipts that are not settled_dry_run.
| Name | Type | Req | Description |
|---|---|---|---|
| reason | string | – | Refund reason |
| receipt_id | string | yes | Receipt id (rcpt_…) |
No output schema declared.
No examples provided.
set_budget Set budget ~89
Overwrite the local spend budget. Changes the ledger limit only. Does not spend money, approve a card, settle a purchase, or contact Stripe or Link. Passing the same amount again does not add to the budget.
| Name | Type | Req | Description |
|---|---|---|---|
| amount_usd | number | yes | Budget amount in USD |
| currency | string | – | Currency code; default USD |
| note | string | – | Optional note for this budget |
No output schema declared.
No examples provided.
How do I install the Rail MCP server?
Rail runs locally as an npm package, launched with npx -y rail-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · rail-mcp
claude mcp add tstockham96-rail-mcp -- npx -y rail-mcp
What is the Rail MCP server?
Rail is an MCP server listed in the public MCP registry as io.github.tstockham96/rail-mcp. Budgets, propose-then-approve, and receipts for agents that buy for a human. Dry-run by default. This page covers its npm package (rail-mcp).
Is the Rail MCP server safe to use?
Rail scores 84 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 25 October 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Rail MCP server expose?
Rail exposes 7 tools: set_budget, get_budget, propose_purchase, list_proposals, decide_proposal, and 2 more. Their descriptions and schemas cost roughly 607 tokens of context every time the server is loaded.
Is the Rail MCP server still maintained?
Rail is still listed as active in the MCP registry. We last reached this channel on 25 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Rail MCP server under?
Rail declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.